Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition
作者： Koray Kavukcuoglu , Marc'Aurelio Ranzato , Yann LeCun
DOI:
关键词: Inference 、 Representation (systemics) 、 Sparse approximation 、 Algorithm 、 Cognitive neuroscience of visual object recognition 、 Image (mathematics) 、 3D single-object recognition 、 Neural coding 、 Computer science 、 Pattern recognition 、 Artificial intelligence 、 Basis function
摘要: Adaptive sparse coding methods learn a possibly overcomplete set of basis functions, such that natural image patches can be reconstructed by linearly combining small subset these bases. The applicability to visual object recognition tasks has been limited because the prohibitive cost optimization algorithms required compute representation. In this work we propose simple and efficient algorithm functions. After training, model also provides fast smooth approximator optimal representation, achieving even better accuracy than exact on tasks.
arxiv.org
harvard.edu
arxiv-vanity.com
toronto.edu 参考文章(18)
Scott Shaobing Chen, David L. Donoho, Michael A. Saunders, Atomic Decomposition by Basis Pursuit SIAM Journal on Scientific Computing. ,vol. 20, pp. 33- 61 ,(1998) , 10.1137/S1064827596304010
Michal Aharon, Michael Elad, Alfred M. Bruckstein, K-SVD and its non-negative variant for dictionary design Wavelets XI. ,vol. 5914, pp. 591411- ,(2005) , 10.1117/12.613878
Joseph F. Murray, Kenneth Kreutz-Delgado, Learning Sparse Overcomplete Codes for Images signal processing systems. ,vol. 45, pp. 97- 110 ,(2006) , 10.1007/S11265-006-0003-Z
Robert Tibshirani, Trevor Hastie, Berwin A. Turlach, Bradley Efron, Jean Michel Loubes, Jean Michel Loubes, Hemant Ishwaran, Robert A. Stine, Keith Knight, Sanford Weisberg, Saharon Rosset, Saharon Rosset, Iain Johnstone, Pascal Massart, Pascal Massart, David Madigan, J. I. Zhu, Greg Ridgeway, Greg Ridgeway, Least angle regression Annals of Statistics. ,vol. 32, pp. 407- 499 ,(2004) , 10.1214/009053604000000067
Julien Mairal, Francis Bach, Jean Ponce, Guillermo Sapiro, Andrew Zisserman, Discriminative learned dictionaries for local image analysis computer vision and pattern recognition. pp. 1- 8 ,(2008) , 10.1109/CVPR.2008.4587652
Geoffrey E Hinton, Ruslan R Salakhutdinov, Reducing the Dimensionality of Data with Neural Networks Science. ,vol. 313, pp. 504- 507 ,(2006) , 10.1126/SCIENCE.1127647
Christopher J. Rozell, Don H. Johnson, Richard G. Baraniuk, Bruno A. Olshausen, Sparse coding via thresholding and local competition in neural circuits Neural Computation. ,vol. 20, pp. 2526- 2563 ,(2008) , 10.1162/NECO.2008.03-07-486
Bruno A. Olshausen, David J. Field, Sparse Coding with an Overcomplete Basis Set: A Strategy Employed by V1 ? Vision Research. ,vol. 37, pp. 3311- 3325 ,(1997) , 10.1016/S0042-6989(97)00169-7
Marc'aurelio Ranzato, Yann L. Cun, Y-lan Boureau, Sparse Feature Learning for Deep Belief Networks neural information processing systems. ,vol. 20, pp. 1185- 1192 ,(2007)
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791